Research status and application of artificial intelligence large models in the oil and gas industry

This article elucidates the concept of large model technology,summarizes the research status of large model technology both domestically and internationally,provides an overview of the application status of large models in vertical industries,outlines the challenges and issues confronted in applying large models in the oil and gas sector,and offers prospects for the application of large models in the oil and gas industry.The existing large models can be briefly divided into three categories:large language models,visual large models,and multimodal large models.The application of large models in the oil and gas industry is still in its infancy.Based on open-source large language models,some oil and gas enterprises have released large language model products using methods like fine-tuning and retrieval augmented generation.Scholars have attempted to develop scenario-specific models for oil and gas operations by using visual/multimodal foundation models.A few researchers have constructed pre-trained foundation models for seismic data processing and interpretation,as well as core analysis.The application of large models in the oil and gas industry faces challenges such as current data quantity and quality being difficult to support the training of large models,high research and development costs,and poor algorithm autonomy and control.The application of large models should be guided by the needs of oil and gas business,taking the application of large models as an opportunity to improve data lifecycle management,enhance data governance capabilities,promote the construction of computing power,strengthen the construction of“artificial intelligence+energy”composite teams,and boost the autonomy and control of large model technology.

The gradual subduction-collision evolution model of Proto-South China Sea and its control on oil and gas

This study involved outcrop,drilling,seismic,gravity,and magnetic data to systematically document the geological records of the subduction process of Proto-South China Sea(PSCS)and establish its evolution model.The results indicate that a series of arc-shaped ophiolite belts and calcalkaline magmatic rocks are developed in northern Borneo,both of which have the characteristics of gradually changing younger from west to east,and are direct signs of subduction and collision of PSCS.At the same time,the subduction of PSCS led to the formation of three accretion zones from the south to the north in Borneo,the Kuching belt,Sibu belt,and Miri belt.The sedimentary formation of northern Borneo is characterized by a three-layer structure,with the oceanic basement at the bottom,overlying the deep-sea flysch deposits of the Rajang–Crocker group,and the molasse sedimentary sequence that is dominated by river-delta and shallow marine facies at the top,recording the whole subduction–collision–orogeny process of PSCS.Further,seismic reflection and tomography also confirmed the subduction and collision of PSCS.Based on the geological records of the subduction and collision of PSCS,combined with the comprehensive analysis of segmented expansion and key tectonic events in the South China Sea,we establish the“gradual”subduction-collision evolution model of PSCS.During the late Eocene to middle Miocene,the Zengmu,Nansha,and Liyue–Palawan blocks were separated by West Baram Line and Balabac Fault,which collided with the Borneo block and Kagayan Ridge successively from the west to the east,forming several foreland basin systems,and PSCS subducted and closed from the west to the east.The subduction and extinction of PSCS controlled the oil and gas distribution pattern of southern South China Sea(SSCS)mainly in three aspects.First,the“gradual”closure process of PSCS led to the continuous development of many large deltas in SSCS.Second,the deltas formed during the subduction–collision of PSCS controlled the development of source rocks in the basins of SSCS.Macroscopically,the distribution and scale of deltas controlled the distribution and scale of source rocks,forming two types of source rocks,namely,coal measures and terrestrial marine facies.Microscopically,the difference of terrestrial higher plants carried by the delta controlled the proportion of macerals of source rocks.Third,the difference of source rocks mainly controlled the distribution pattern of oil and gas in SSCS.Meanwhile,the difference in the scale of source rocks mainly controlled the difference in the amount of oil and gas discoveries,resulting in a huge amount of oil and gas discoveries in the basin of SSCS.Meanwhile,the difference of macerals of source rocks mainly controlled the difference of oil and gas generation,forming the oil and gas distribution pattern of“nearshore oil and far-shore gas”.

Prediction of Sedimentary Microfacies Distribution by Coupling Stochastic Modeling Method in Oil and Gas Energy Resource Exploitation

In view of the problem that a single modeling method cannot predict the distribution of microfacies, a new idea of coupling modeling method to comprehensively predict the distribution of sedimentary microfacies was proposed, breaking the tradition that different sedimentary microfacies used the same modeling method in the past. Because different sedimentary microfacies have different distribution characteristics and geometric shapes, it is more accurate to select different simulation methods for prediction. In this paper, the coupling modeling method was to establish the distribution of sedimentary microfacies with simple geometry through the point indicating process simulation, and then predict the microfacies with complex spatial distribution through the sequential indicator simulation method. Taking the DC block of Bohai basin as an example, a high-precision reservoir sedimentary microfacies model was established by the above coupling modeling method, and the model verification results showed that the sedimentary microfacies model had a high consistency with the underground. The coupling microfacies modeling method had higher accuracy and reliability than the traditional modeling method, which provided a new idea for the prediction of sedimentary microfacies.

Development of Dispersion Models for the Simulation of Fluid Catalytic Cracking of Vacuum Gas Oil in Riser Reactor

Dispersion models for the simulation of an industrial Fluid Catalytic Cracking Riser Reactor have been developed. The models were developed based on the principle of conservation of mass and energy on the reacting species due to bulk flow and axial dispersion. The four-lump kinetic scheme was used to describe the cracking reactions occurring in the reactor. The model equations were a set of parabolic Ordinary Differential Equations which were reduced to first order differential equations by appropriate substitutions and integrated numerically using 4th order Runge Kutta algorithm using Visual Basic 6.0. Results obtained showed a maximum percentage deviation ranging from 0.31% to 5.7% between model predictions and industrial plant data indicating reasonable agreement. Simulation of model at various operating parameters gave optimum gasoline yield of 45.6% of the most significant variable of temperature (658 K), superficial velocity (0.1 m/s), catalyst to gas oil ratio (7.0) and diffusion coefficient of 0.23 m2/s.

Development characteristics, models and strategies for overseas oil and gas fields

Based on about 20 years of accumulated experience and knowledge of oil and gas field development in overseas countries and regions for China's oil companies, the development features, ideas, models and plan designing strategies of overseas oil and gas fields were comprehensively summarized. Overseas oil and gas field development has ten major features, such as non-identity project resource, diversity of contract type, complexity of cooperation model, and so on. The overseas oil and gas field development aims at the maximization of production and benefit during the limited contract period, so the overseas oil and gas field development models are established as giving priority to production by natural energy, building large-scale production capacity, putting into production as soon as possible, realizing high oil production recovery rate, and achieving rapid payback period of investment. According to the overseas contract mode, a set of strategies for overseas oil and gas field development plans were made. For tax systems contracts, the strategy is to adopt the mode of "first fat and then thinner, easier in the first and then harder", that is, early investment pace, production increase rate, development workload and production were decided by the change of tax stipulated in the contract. For production share contracts, the strategy is to give priority to high production with a few wells at a high production recovery rate to increase the cost-oil and shorten the period of payback. For technical service contracts, the strategy is that the optimal production target and workload of the project were determined by the return on investment, so as to ensure that the peak production and stable production periods meet the contract requirements.

Whole petroleum system and ordered distribution pattern of conventional and unconventional oil and gas reservoirs

The classical source-to-trap petroleum system concept only considers the migration and accumulation of conventional oil and gas in traps driven dominantly by buoyance in a basin,although revised and improved,even some new concepts as composite petroleum system,total petroleum system,total composite petroleum system,were proposed,but they do not account for the vast unconventional oil and gas reservoirs within the system,which is not formed and distributed in traps dominantly by buoyancedriven.Therefore,the petroleum system concept is no longer adequate in dealing with all the oil and gas accumulations in a basin where significant amount of the unconventional oil and gas resources are present in addition to the conventional oil and gas accumulations.This paper looked into and analyzed the distribution characteristics of conventional and unconventional oil/gas reservoirs and their differences and correlations in petroliferous basins in China and North America,and then proposed whole petroleum system(WPS)concept,the WPS is defined as a natural system that encompasses all the conventional and unconventional oil and gas,reservoirs and resources originated from organic matter in source rocks,the geological elements and processes involving the formation,evolution,and distribution of these oil and gas,reservoirs and resources.It is found in the WPS that there are three kinds of hydrocarbons dynamic fields,three kinds of original hydrocarbons,three kinds of reservoir rocks,and the coupling of these three essential elements lead to the basic ordered distribution model of shale oil/gas reservoirs contacting or interbeded with tight oil/gas reservoirs and separated conventional oil/gas reservoirs from source rocks upward,which is expressed as“S\T-C”.Abnormal conditions lead to other three special ordered distribution models:The first is that with shale oil/gas reservoirs separated from tight oil/gas reservoirs.The second is that with two direction ordered distributions from source upward and downward.The third is with lateral distribution from source outside.

Improved AHP–TOPSIS model for the comprehensive risk evaluation of oil and gas pipelines

A comprehensive and objective risk evaluation model of oil and gas pipelines based on an improved analytic hierarchy process(AHP)and technique for order preference by similarity to an ideal solution(TOPSIS)is established to identify potential hazards in time.First,a barrier model and fault tree analysis are used to establish an index system for oil and gas pipeline risk evaluation on the basis of five important factors:corrosion,external interference,material/construction,natural disasters,and function and operation.Next,the index weight for oil and gas pipeline risk evaluation is computed by applying the improved AHP based on the five-scale method.Then,the TOPSIS of a multi-attribute decision-making theory is studied.The method for determining positive/negative ideal solutions and the normalized equation for benefit/cost indexes is improved to render TOPSIS applicable for the comprehensive risk evaluation of pipelines.The closeness coefficient of oil and gas pipelines is calculated by applying the improved TOPSIS.Finally,the weight and the closeness coefficient are combined to determine the risk level of pipelines.Empirical research using a long-distance pipeline as an example is conducted,and adjustment factors are used to verify the model.Results show that the risk evaluation model of oil and gas pipelines based on the improved AHP–TOPSIS is valuable and feasible.The model comprehensively considers the risk factors of oil and gas pipelines and provides comprehensive,rational,and scientific evaluation results.It represents a new decision-making method for systems engineering in pipeline enterprises and provides a comprehensive understanding of the safety status of oil and gas pipelines.The new system engineering decision-making method is important for preventing oil and gas pipeline accidents.

Application of Discrete Lumped Kinetic Modeling on Vacuum Gas Oil Hydrocracking

The kinetic model of vacuum gas oil （VGO） hydrocracking based on discrete lumped approach was investigated, and some improvement was put forward at the same time in this article. A parallel reaction scheme to describe the conver- sion of VGO into products （gases, gasoline, and diesel） proposed by Orochko was used. The different experimental data were analyzed statistically and then the product distribution and kinetic parameters were simulated by available data. Fur- thermore, the kinetic parameters were correlated based on the feed property, reaction temperature, and catalyst activity. An optimization code in Matlab 2011b was written to fine-me these parameters. The model had a favorable ability to predict the product distribution and there was a good agreement between the model predictions and experiment data. Hence, the ki- netic parameters indeed had something to do with feed properties, reaction temperature and catalyst activity.

Gas injection for enhanced oil recovery in two-dimensional geology-based physical model of Tahe fractured-vuggy carbonate reservoirs:karst fault system

Gas injection serves as a main enhanced oil recovery(EOR)method in fractured-vuggy carbonate reservoir,but its effect differs among single wells and multi-well groups because of the diverse fractured-vuggy configuration.Many researchers conducted experiments for the observation of fluid flow and the evaluation of production performance,while most of their physical models were fabricated based on the probability distribution of fractures and caves in the reservoir.In this study,a two-dimensional physical model of the karst fault system was designed and fabricated based on the geological model of TK748 well group in the seventh block of the Tahe Oilfield.The fluid flow and production performance of primary gas flooding were discussed.Gas-assisted gravity flooding was firstly introduced to take full use of gas-oil gravity difference,and its feasibility in the karst fault system was examined.Experimental results showed that primary gas flooding created more flow paths and achieved a remarkable increment of oil recovery compared to water flooding.Gas injection at a lower location was recommended to delay gas breakthrough.Gas-assisted gravity flooding achieved more stable gas-displacing-oil because oil production was at a lower location,and thus,the oil recovery was further enhanced.

Optimization of operational strategies for rich gas enhanced oil recovery based on a pilot test in the Bakken tight oil reservoir

Horizontal well drilling and multistage hydraulic fracturing have been demonstrated as effective approaches for stimulating oil production in the Bakken tight oil reservoir.However,after multiple years of production,primary oil recovery in the Bakken is generally less than 10%of the estimated original oil in place.Gas huff‘n’puff(HnP)has been tested in the Bakken Formation as an enhanced oil recovery(EOR)method;however,most field pilot test results showed no significant incremental oil production.One of the factors affecting HnP EOR performance is premature gas breakthrough,which is one of the most critical issues observed in the field because of the presence of interwell fractures.Consequently,injected gas rapidly reaches adjacent production wells without contacting reservoir rock and increasing oil recovery.Proper conformance control is therefore needed to avoid early gas breakthrough and improve EOR performance.In this study,a rich gas EOR pilot in the Bakken was carefully analyzed to collect the essential reservoir and operational data.A simulation model with 16 wells was then developed to reproduce the production history and predict the EOR performance with and without conformance control.EOR operational strategies,including single-and multiple-well HnP,with different gas injection constraints were investigated.The simulation results of single-well HnP without conformance control showed that a rich gas injection rate of at least 10 MMscfd was needed to yield meaningful incremental oil production.The strategy of conformance control via water injection could significantly improve oil production in the HnP well,but injecting an excessive amount of water also leads to water breakthrough and loss of oil production in the offset wells.By analyzing the production performance of the wells individually,the arrangement of wells was optimized for multiple-well HnP EOR.The multiwell results showed that rich gas EOR could improve oil production up to 7.4%by employing conformance control strategies.Furthermore,replacing rich gas with propane as the injection gas could result in 14%of incremental oil production.

Investment in deepwater oil and gas exploration projects:a multi-factor analysis with a real options model

Deepwater oil and gas projects embody high risks from geology and engineering aspects, which exert substantial influence on project valuation. But the uncer- tainties may be converted to additional value to the projects in the case of flexible management. Given the flexibility of project management, this paper extends the classical real options model to a multi-factor model which contains oil price, geology, and engineering uncertainties. It then gives an application example of the new model to evaluate deepwater oil and gas projects with a numerical analytical method. Compared with other methods and models, this multi-factor real options model contains more project information. It reflects the potential value deriving not only from oil price variation but also from geology and engi- neering uncertainties, which provides more accurate and reliable valuation information for decision makers.

Solubility and mass transfer of H2, CH4, and their mixtures in vacuum gas oil: An experimental and modeling study

In this work,the solubility data and liquid-phase mass transfer coefficients of hydrogen(H2),methane(CH4)and their mixtures in vacuum gas oil(VGO)at temperatures(353.15-453.15 K)and pressures(1-7 MPa)were measured,which are necessary for catalytic cracking process simulation and design.The solubility of H2 and CH4 in VGO increases with the increase of pressure,but decreases with the increase of temperature.Henry’s constants of H2 and CH4 follow the relation of In H=-413.05/T+5.27 and In H=-990.67/T+5.87,respectively.The molar fractions of H2 and system pressures at different equilibrium time were measured to estimate the liquid-phase mass transfer coefficients.The results showed that with the increase of pressure,the liquid-phase mass transfer coefficients increase.Furthermore,the solubility of H2 and CH4 in VGO was predicted by the predictive COSMO-RS model,and the predicted values agree well with experimental data.In addition,the gas-liquid equilibrium(GLE)for H2+CH4+VGO system at different feeding gas ratios in volume fraction(i.e.,H285%+CH415%and H290%+CH410%)was measured.The selectivity of H2 to CH4 predicted by the COSMO-RS model agrees well with experimental data.This work provides the basic thermodynamic and dynamic data for fuel oil catalytic cracking processes.

Bargaining strategy of oil companies in international oil and gas development Projects-Based on a bilateral bargaining model

Bargaining between the host country and oil companies is very common to international oil and gas development projects.The existence of information asymmetry gives the host country an endogenous bargaining advantage.Foreign oil companies might change their unfavorable negotiating position by changing the order of bidding and adjusting bidding strategies.This paper introduces both factors into a bilateral bargaining model to study the impact of information asymmetry and bidding order on the strategy and equilibrium returns of oil companies.According to the ownership of the right to bid first,two scenarios are designed for the model to compare the equilibrium returns of the host country and oil companies.The results show that:1)There is a first-mover advantage in the process of bilateral bidding,so oil companies better bid first;2)The information asymmetry will lead to a higher nominal income ratio of oil companies and a lower nominal income ratio of the host country,but it doesn’t affect the total income ratio at all.

Predictive Model to Evaluate Accommodation of Conflict Management Strategies and Board Performance of Oil and Gas Companies in Port Harcourt

This paper evaluates accommodation of conflict management strategies and board performances in oil and gas sector.The study details the re­flection of effectiveness,efficiency and productivity as the answer to thorough efficiency in accommodation of conflict management in oil and gas sector,these parameters in the system express their efficacy on con­flict management in these multinationals,this implies that for thorough efficiency,these variables must work simultaneously for effective and efficient in structural organization that can be a leading multinational sector in oil and gas environment.The study observed Linearized result from graphical representation explaining predominant lower efficiency and little higher efficiency in accommodation of conflict management in oil and gas companies.These experiences from the study monitor the system from generated simulation values that describe the growth rates in exponential phase of accommodation conflict strategic management.Despite exponential phase the results experienced lower parameters,when comparing on its variations showing its poor efficiency as observed in the study.Few periods observed higher effective accommodation on conflict strategic management.The developed model stimulation values were subjected to validation and both parameters generated favourable fits correlation,the study expressed the deficiency on accommodation of conflict management strategy thus developed models that can monitor the fluctuation and progressive state of accommodation on conflict manage­ment strategy,it defines the reflection of other parameters that express the behaviour of the system in terms of conceptual approach to monitor these type of strategic management in oil and gas companies.

Investigation of flue gas water-alternating gas (flue gas–WAG) injection for enhanced oil recovery and multicomponent flue gas storage in the post-waterflooding reservoir

Flue gas fooding is one of the important technologies to improve oil recovery and achieve greenhouse gas storage.In order to study multicomponent fue gas storage capacity and enhanced oil recovery(EOR)performance of fue gas water-alternating gas(fue gas-WAG)injection after continuous waterfooding in an oil reservoir,a long core fooding system was built.The experimental results showed that the oil recovery factor of fue gas-WAG fooding was increased by 21.25%after continuous waterfooding and fue gas-WAG fooding could further enhance oil recovery and reduce water cut signifcantly.A novel material balance model based on storage mechanism was developed to estimate the multicomponent fue gas storage capacity and storage capacity of each component of fue gas in reservoir oil,water and as free gas in the post-waterfooding reservoir.The ultimate storage ratio of fue gas is 16%in the fue gas-WAG fooding process.The calculation results of fue gas storage capacity showed that the injection gas storage capacity mainly consists of N_(2) and CO_(2),only N_(2) exists as free gas phase in cores,and other components of injection gas are dissolved in oil and water.Finally,injection strategies from three perspectives for fue gas storage,EOR,and combination of fue gas storage and EOR were proposed,respectively.

Risk measurement of international oil and gas projects based on the Value at Risk method

International oil and gas projects feature high capital-intensity, high risks and contract diversity. Therefore, in order to help decision makers make more reasonable decisions under uncertainty, it is necessary to measure the risks of international oil and gas projects. For this purpose, this paper constructs a probabilistic model that is based on the traditional economic evaluation model, and introduces value at risk(VaR) which is a valuable risk measure tool in finance, and applies Va R to measure the risks of royalty contracts, production share contracts and service contracts of an international oil and gas project. Besides, this paper compares the influences of different risk factors on the net present value(NPV) of the project by using the simulation results. The results indicate:(1) risks have great impacts on the project's NPV, therefore, if risks are overlooked, the decision may be wrong.(2) A simulation method is applied to simulate the stochastic distribution of risk factors in the probabilistic model. Therefore, the probability is related to the project's NPV, overcoming the inherent limitation of the traditional economic evaluation method.(3) VaR is a straightforward risk measure tool, and can be applied to evaluate the risks of international oil and gas projects. It is helpful for decision making.

Deep-water gravity flow deposits in a lacustrine rift basin and their oil and gas geological significance in eastern China

The types,evolution processes,formation mechanisms,and depositional models of deep-water gravity flow deposits in a lacustrine rift basin are studied through core observation and systematic analysis.Massive transport of slide and slump,fluid transport of debris flow and turbidity currents are driven by gravity in deep-water lacustrine environment.The transformation between debris flow and turbidity current,and the transformation of turbidity current between supercritical and subcritical conditions are the main dynamic mechanisms of gravity flow deposits in a lake basin.The erosion of supercritical turbidity current controls the formation of gravity-flow channel.Debris flow deposition gives rise to tongue shape lobe rather than channel.Deep-water gravity flow deposits are of two origins,intrabasinal and extrabasinal.Intrabasinal gravity flow deposits occur as single tongue-shape lobe or fan of stacking multiple lobes.Extrabasinal gravity-flow deposits occur as sublacustrine fan with channel or single channel sand body.However,the nearshore subaqueous fan is characterized by fan of stacking multiple tongue shape lobes without channel.The differential diagenesis caused by differentiation in the nearshore subaqueous fan facies belt results in the formation of diagenetic trap.The extrabasinal gravity flow deposits are one of the important reasons for the abundant deep-water sand bodies in a lake basin.Slide mass-transport deposits form a very important type of lithologic trap near the delta front often ignored.The fine-grained sediment caused by flow transformation is the potential"sweet spot"of shale oil and gas.

Modeling the Flow Regime Near the Source in Underwater Gas Releases

Recent progress in calculating gas bubble sizes in a plume, based on phenomenological approaches using the release conditions is a significant improvement to make the gas plume models self-reliant. Such calculations require details of conditions Near the Source of Plume （NSP）; （i.e. the plume/jet velocity and radius near the source）, which inspired the present work. Determining NSP conditions for gas plumes are far more complex than that for oil plumes due to the substantial density difference between gas and water. To calculate NSP conditions, modeling the early stage of the plume is important. A novel method of modeling the early stage of an underwater gas release is presented here. Major impact of the present work is to define the correct NSP conditions for underwater gas releases, which is not possible with available methods as those techniques are not based on the physics of flow region near the source of the plume/jet. We introduce super Gaussian profiles to model the density and velocity variations of the early stages of plume, coupled with the laws of fluid mechanics to define profile parameters. This new approach, models the velocity profile variation from near uniform, across the section at the release point to Gaussian some distance away. The comparisons show that experimental data agrees well with the computations.

Molecular reconstruction of vacuum gas oils using a general molecule library through entropy maximization

Vacuum gas oil(VGO)is the most important feedstock for hydrocracking processes in refineries,but its molecular composition cannot be fully acquired by current analysis techniques owing to its complexity.In order to build an accurate and reliable molecular-level kinetic model for reactor design and process optimization,the molecular composition of VGO has to be reconstructed based on limited measurements.In this study,a modified stochastic reconstruction-entropy maximization(SR-REM)algorithm was applied to reconstruct VGOs,with generation of a general molecule library once and for all via the SR method at the first step and adjustment of the molecular abundance of various VGOs via the REM method at the second step.The universality of the molecule library and the effectiveness of the modified SR-REM method were validated by fifteen VGOs(three from the literature)from different geographic regions of the world and with different properties.The simulated properties(density,elemental composition,paraffin-naphthene-aromatics distribution,boiling point distribution,detailed composition of naphthenes and aromatics in terms of ring number as well as composition of S-heterocycles)are in good agreement with the measured counterparts,showing average absolute relative errors of below 10%for each property.

A 3D basin modeling study of the factors controlling gas hydrate accumulation in the Shenhu Area of the South China Sea

Great advancement has been made on natural gas hydrates exploration and test production in the northern South China Sea.However,there remains a lot of key questions yet to be resolved,particularly about the mechanisms and the controls of gas hydrates enrichment.Numerical simulaution would play signficant role in addressing these questions.This study focused on the gas hydrate exploration in the Shenhu Area,Northern South China Sea.Based on the newly obtained borehole and multichannel reflection seismic data,the authors conducted an integrated 3D basin modeling study on gas hydrate.The results indicate that the Shenhu Area has favorable conditions for gas hydrate accumulation,such as temperature,pressure,hydrocarbon source,and tectonic setting.Gas hydrates are most concentrated in the Late Miocene strata,particularly in the structual highs between the Baiyun Sag and the Liwan Sag,and area to the south of it.It also proved the existence of overpressure in the main sag of source rocks,which was subject to compaction disequilibrium and hydrocarbon generation.It also shown that the regional fault activity is not conducive to gas hydrate accumulation due to excess gas seepage.The authors conjecture that fault activity may slightly weaken overpressure for the positive effect of hydrocarbon expulsion and areas lacking regional fault activity have better potential.